Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.9176. Min Act: -0.1700

Data Index: 193188 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.9397. Min Act: -0.1700

Data Index: 3247814 (Open Web Text)

Max Activating Token Index: 809

Text #2

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8722. Min Act: -0.1700

Data Index: 384157 (Open Web Text)

Max Activating Token Index: 862

Text #3

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.9011. Min Act: -0.1700

Data Index: 1367079 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8559. Min Act: -0.1700

Data Index: 1361583 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8328. Min Act: -0.1700

Data Index: 276897 (Open Web Text)

Max Activating Token Index: 318

Text #6

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8644. Min Act: -0.1700

Data Index: 2874088 (Open Web Text)

Max Activating Token Index: 249

Text #7

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8422. Min Act: -0.1700

Data Index: 7314511 (Open Web Text)

Max Activating Token Index: 97

Text #8

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7901. Min Act: -0.1700

Data Index: 7999918 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8128. Min Act: -0.1700

Data Index: 7328588 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7986. Min Act: -0.1700

Data Index: 6161311 (Open Web Text)

Max Activating Token Index: 370

Text #11

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8068. Min Act: -0.1700

Data Index: 6110504 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7591. Min Act: -0.1700

Data Index: 2139059 (Open Web Text)

Max Activating Token Index: 902

Text #13

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7773. Min Act: -0.1700

Data Index: 6465613 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7769. Min Act: -0.1700

Data Index: 164825 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7768. Min Act: -0.1700

Data Index: 2666808 (Open Web Text)

Max Activating Token Index: 119

Text #16

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7845. Min Act: -0.1700

Data Index: 6009498 (Open Web Text)

Max Activating Token Index: 266

Text #17

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7584. Min Act: -0.1700

Data Index: 5335744 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7560. Min Act: -0.1700

Data Index: 6568775 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7409. Min Act: -0.1700

Data Index: 645328 (Open Web Text)

Max Activating Token Index: 220